mlsanityData to 14 Oct 2026

Sensitivity-Aware Post-Training Quantization for Deep Neural Networks

arXiv 2509.05576 ↗First posted 6 Sep 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high compression ratios, incurring significant computational complexity and resource overhead, which limits applicability in resource-constrained edge computing and real-time inference scenarios. This paper proposes an efficient PTQ method guided by parameter sensitivity analysis. The approach prioritizes quantization of high-sensitivity parameters, leveraging unquantized low-sensitivity parameters to compensate for quantization errors, thereby mitigating accuracy degradation. Furthermore, by exploiting column-wise clustering of parameter sensitivity, the method introduces a row-parallel quantization framework with a globally shared inverse Hessian matrix update mechanism, reducing computational complexity by an order of magnitude. Experimental results on ResNet-50 and YOLOv5s demonstrate a 20-200-fold quantization speedup over the Optimal Brain Quantization baseline, with mean accuracy loss below 0.3%, confirming the method's efficacy in balancing efficiency and accuracy.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 6 Sep 2025.

Builds on

21 of 33 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  9. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  10. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  11. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  12. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 324
9 more
  1. 2022Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruningcited by 322
  2. 2021Post-Training Quantization for Vision Transformercited by 278
  3. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
  4. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
  5. 2017Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeoncited by 221
  6. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 193
  7. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 151
  8. 2022Overcoming Oscillations in Quantization-Aware Trainingcited by 119
  9. 2019Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorizationcited by 45

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Mixed-Precision Quantization for Language Models: Techniques and Prospectscited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2022QFT: Post-training quantization via fast joint finetuning of all degrees of freedom
  2. 2023Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
  3. 2021Post-Training Sparsity-Aware Quantization
  4. 2021A White Paper on Neural Network Quantization
  5. 2023Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization
  6. 2026Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models
  7. 2024COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
  8. 2025Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos